Search

Best harness engineering for Claude Code. Work like a corporation team, not just a club.

Maestro — Autonomous AI agent operating system. Deploy AI employees on dedicated Mac minis.

Human approval gate for AI agent actions. Drop-in protection against prompt injection for any API key.

Multi-agent AI orchestration with confidence scoring for TypeScript

MeowKit CLI — scaffold, upgrade, and manage your AI agent toolkit

Agent identity and on-chain memory protocol for X1 blockchain

Self-hosted E2B sandbox integration for Deep Agents

Anthropic's Advisor Strategy as a drop-in DeepAgents middleware — pair a powerful advisor with a fast executor

Vibe Hacker — Terminal AI cybersecurity assistant. Free models, autonomous agent, multi-provider rotation.

Classify web traffic into humans, bots, AI agents, and programmatic clients from access logs and HTTP header signals

BuildShip Agent SDK — core + React bindings.

Production-grade AI agent runtime — multi-turn tool-calling, persistent memory, and multi-model routing

Python ACP client library — connect to AI coding agents (Claude Code, Gemini, OpenCode, OpenClaw, Cursor, Codex, Qwen, Kimi, Codebuddy, Cline, Copilot, Minion, Vibe, Nova, Crow) with zero session overhead

CLI for agents to create and manage MoonPay local wallets for ERC-8004 and x402 payments

Tree-structured multi-agent runtime with a FastAPI core, LangChain agents, and event-driven executors.

ConsistentRAG: Improving factual consistency in RAG through knowledge graph grounding and multi-agent refinement

LLM-based replication framework for behavioral economics experiments

Production-grade fault tolerance for AI agents — circuit breakers, LLM-aware retry, idempotency, and loop detection

Drop-in prompt injection defense for LLM apps and AI agents — detect, block, and audit injection attacks in real time

Minimal HTTP client for BRADY Phase 3 external agents